Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversations

Effective manager-employee communication is critical for retaining high performers and developing underperformers, yet training managers in these skills remains costly. Text-based chatbots offer a scalable approach but cannot provide realistic rehearsal: managers need to practice speaking aloud to build confidence before high-stakes conversations. In this paper, we propose Conversation Coach, a voice-first AI system that enables managers to rehearse difficult workplace conversations in a realistic spoken format. The system addresses three challenges: achieving low-latency interactions with strong language understanding, enabling adaptive conversations through configurable bot personalities that simulate different employee types, and generating personalized feedback on content and policy compliance. We compare an end-to-end speech-to-speech model with a cascaded approach combining automatic speech recognition, a large language model, and text-to-speech synthesis. The end-to-end approach achieves 3$\times$ lower median (P50) latency with native barge-in capability at an estimated 8$\times$ lower cost, while the cascaded approach offers superior reasoning essential for coaching quality. We deployed the cascaded architecture in production, where 40,000+ managers used it over six months, with adoption patterns indicating selective use for difficult conversations.

Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect. We ask when this control path exposes enough concurrent work for GPU execution, and what changes when a GPU-computed route decision remains on device. We formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A. Under zero service time, unlimited capacity, and equal relative launch deadlines, a specialized dynamic program computes P* exactly. In a stationary Poisson replay of one pinned 851-session public trace panel, the primary condition at 100,000 target active sessions, K=256, and a 50 ms launch deadline gives F=30.19%, P*=43.00%, and U=45.85%. Exact packing recovers 81.83% of the opportunity lost at fixed window boundaries. The outcome-derived route key is a conditioning proxy, not proof of executable identity. A separate mechanism study keeps a GPU-computed binary decision on device instead of returning four bytes to the host and redispatching. Across four named GPU placements, the device-resident path is faster in all 36 configurations; within-placement row-median ratios range from 1.19x to 2.39x. Across both admissible mechanisms, all 14,557,440 tested batched invocations match a separately implemented host oracle. A fixed nested device graph that removes no host decision is slower in all 60 configurations across five placements. Together, the studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement. A joined finite online runtime is required to measure A, CPU displacement, and service-level benefit.

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving

Large language model agents increasingly act through stateful tools, yet model generation and environment execution remain serialized at every step. As decoding accelerates, tool execution becomes a growing bottleneck. Existing action- or observation-only speculation leaves much of this latency exposed: value is concentrated in a few slow calls, some outcomes emerge only through execution, and longer lookahead typically requires an increasingly unlikely chain of action predictions. We present AOSpec, a lossless framework that co-speculates actions and observations across the full agent-environment loop. Expected Value Decoding (EVD) directs observation speculation toward outcomes with the greatest expected latency benefit, optimizing expected time hidden rather than hit rate. For outcomes only execution can reveal, AOSpec launches latency-critical target actions in isolated forks that contain their effects, while Joint Action-State Verification (JASV) verifies both the action and its origin state against committed execution before reuse. JASV recasts long-horizon action dependency from full-chain prediction into target action-state verification, breaking the lookahead--accuracy tradeoff and unlocking long-range overlap without sacrificing serial semantics. Across Terminal-Bench serving settings spanning four harnesses, five actor models, and five serving speeds, AOSpec outperforms every practical baseline, reducing mean end-to-end latency by 11.8-32.5% and p99 latency by up to 42.8%. Its gains increase as decoding accelerates, and its observation model transfers from Terminal-Bench to SWE-bench Verified without retraining.

Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees

Computer-use agents often fail on transient GUI events because they produce the correct action only after the relevant window has already closed. We identify the main cause as expensive autoregressive decoding on the decision-time critical path. We propose Adaptive Anticipatory Policy Trees (AAPT), which eliminates this delay without modifying the underlying model. During idle screen periods, the same frozen multimodal model constructs a bounded conditional policy tree with observable guards, pre-authorized actions, and branch-specific deadlines. The tree is sized to cover the model's own decoding latency. When an event occurs, a lightweight observer matches change-gated frames to a prepared branch and immediately executes the corresponding action without generating new text. In paired trials with pre-registered endpoints and exact McNemar tests, AAPT improves the success rate from 0.50 to 0.79 within a contested decision window ($p=1.8\times10^{-3}$), while producing no incorrect actions. Both open-loop and predict-and-replan baselines achieve zero success because they still decode during execution. A preparation-time sweep shows that the gain emerges where the latency-based tree-sizing rule predicts, and ablations reveal three key requirements: fast observer decoding, valid tree planning, and accurate branch routing. A pre-registered oracle probe rejects our initial hypothesis and instead points to branch routing as the causal bottleneck. We further reproduce the effect on an independent general-purpose multimodal model over 126 paired trials ($p=4.9\times10^{-13}$). On an external benchmark, AAPT matches the overall performance of a reactive baseline, although the two methods exhibit complementary strengths. Together, these results suggest that AAPT performs best when candidate actions can be enumerated in advance, whereas reactive execution remains stronger when they cannot.

Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL

Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predicting and pre-executing an agent's next tool call if the prediction matches the agent's eventual tool call, but existing speculators are typically separate draft models or cached traces that are poorly aligned with the deployed agent's own behavior. We identify this speculator-agent gap and show that the target agent itself is a strong next-call speculator. This points to a simpler design: unifying the agent and speculator within the same model. In this paper, we introduce the self-speculating agent, a single model that both solves tasks in agent mode and predicts its next tool call from partial trajectories in speculator mode, fully reusing prefix KV cache. To enable this dual-mode agent without degrading performance, we propose a joint agent-speculator reinforcement learning method, which derives speculation targets from the agent's own rollouts and alternates agent and speculator updates. Across agentic search QA and conversational tool-use agentic tasks, our method improves average next tool-call Hit@1 from 44.1 to 61.2 for Qwen3-4B and from 48.9 to 66.3 for Qwen3.5-4B, while preserving agent task success.

Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems

Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that self-evolving agents can make industrial LLM systems faster, more reliable, and easier to operate.

Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents

Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn. We study the regime where memory moves inside the loop, read and written on every step. The obstacle has always been latency: networked stores answer in tens to hundreds of milliseconds, and in-loop retrieval can inflate end-to-end latency by up to 83x when retrieval is expensive. Prior work manages that cost rather than questioning it: serving-layer scheduling hides it, "memory-first" designs ration retrieval to once per turn. We argue latency is a property of where the store lives, not the in-loop pattern: an in-process store answers in ~100us, three orders of magnitude below the network regime, and at that speed the per-step tax collapses. By the extended-mind thesis's parity principle, a store fast enough to be constantly and directly available becomes extended working memory, not a tool the agent merely consults. The premise is causal: holding a fixed per-turn memory-latency budget and varying only the store's answer speed, redundant actions rise monotonically with latency - 0.0 of 12 at in-process speed, 7.2 of 12 at a 110ms cloud round trip (gpt-5-nano, gpt-5-mini; exact permutation p=0.0079). We demonstrate the regime end-to-end: across four GPT-5-class models under a bounded window, recall improves from 0/5 to 3.6-4.8/5 with in-loop memory, store ops at p50 80-165us - though an instructed restate-every-reply baseline also solves it perfectly, at a token cost that grows with the working set. The store never lost a fact in any run (244 of 244 writes kept); every miss traces to the agent's read policy, not the store. Our measurements also relocate the bottleneck: the dominant per-step cost is embedding (~200-400ms over the network); pairing the in-process store with a small local embedder returns the complete operation to a measured ~40us.

DynAMO:Dynamic Asset Management Orchestration via Topological Multi-Agent Scheduling

While LLM-powered agents offer end-to-end automation for industrial asset lifecycles, real-world Industry 4.0 deployment is hindered by latency, concurrency instability, and safety risks. We present DynAMO (Dynamic Asset Management Orchestration), a deployment-ready engine using a Plan-then-Execute architecture to generate verifiable workflow graphs. DynAMO supports both SequentialWorkflow (topological execution) and ParallelWorkflow (dependency-aware concurrency). By dynamically identifying independent tasks, DynAMO preserves structural correctness and safety while significantly improving efficiency through controlled reasoning overlap. Across six controlled experiments on the AssetOpsBench industrial benchmark, DynAMO demonstrates substantial performance and robustness gains. Parallel execution reduces end-to-end latency by a median of 1.6x over sequential orchestration, rising to 1.8x on highly parallelizable workflows. After instrumenting external tool calls with realistic latencies, a latency decomposition shows that LLM reasoning and orchestration still account for more than 90% of execution time, identifying model inference as the primary system bottleneck. Structured context pruning reduces inference latency by approximately 30%, and DynAMO maintains correct functional behaviour (task completion, agent sequencing, and output quality) while exhibiting graceful degradation under controlled fault injection. Reproducibility analysis further confirms stable execution under repeated runs, with parallel scheduling reducing latency variance. These findings establish DynAMO as a practical blueprint for scalable, safe, and latency-aware agent deployment in Industry 4.0 automation pipelines. Code is available at: https://github.com/kushwaha001/DynAMO

Workload-Aware Caching for Multi-Agent Systems

Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries. However, existing cache eviction policies treat all cached entries uniformly based on access history, ignoring structural and workload signals uniquely available in agentic execution environments. We present a workload-aware eviction policy that combines three signals, namely recomputation cost, DAG dependency count, and agent invocation frequency, into a unified scoring function that retains the most valuable entries under memory constraints. Evaluated across three multi-agent benchmarks spanning diverse reuse regimes, our policy reduces latency by up to 64.7% relative to the uncached baseline and achieves on average a 31.1% latency reduction over the next best finite-capacity baseline, while approaching the performance of an unbounded cache and maintaining accuracy on par with or exceeding all competing finite-capacity methods. We further show that workload-aware content caching is complementary to other agentic system optimization methods, including plan-level caching and parallel agent execution, with each technique targeting a distinct efficiency bottleneck in multi-agent pipelines.

Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling

Computer-use agents (CUA) automate tasks specified with natural language such as "order the cheapest item from Taco Bell" by generating sequences of calls to tools such as click, type, and scroll on a browser. Current implementations follow a sequential fetch-screenshot-execute loop where each iteration requires an LLM call, resulting in high latency and frequent errors from incorrect tool use. We present agent just-in-time (JIT) compilation, an alternative that compiles task descriptions directly into executable code that is free to include LLM calls, tool calls, and parallelization. Our approach comprises three components: (1) JIT-Planner, which generates multiple code plans, validates each against tool specifications, and selects the minimum-cost candidate; (2) JIT-Scheduler, which explores parallelization strategies via Monte Carlo cost estimation from learned latency distributions; and (3) an invariant-enforcing tool protocol specifying precondition and postcondition state requirements that reduce the rate of generating plans with incorrect tool use. Across 5 web applications, JIT-Planner achieves $10.4\times$ speedup and $+28\%$ accuracy over Browser-Use, while JIT-Scheduler achieves $2.4\times$ speedup and $+9\%$ accuracy over OpenAI CUA.

Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines

Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure modes, forecasting tools, and domain-specific agents. We evaluate this problem on AssetOpsBench (AOB), an industrial agent benchmark whose plan-execute pipeline exposes repeated overhead from tool discovery, LLM planning, MCP tool execution, and final summarization. Existing LLM caching techniques such as KV-cache reuse and embedding-based semantic caching were designed for chatbot serving and break down when output validity depends on time, asset, or sensor parameters. We propose two complementary optimization layers for AOB plan-execute pipelines: a temporal semantic cache and a set of MCP workflow optimizations combining disk-backed tool-discovery caching and dependency-aware parallel step execution. MCP workflow optimizations corresponded to a 1.67x speedup and reduced median end-to-end latency by about 40.0% while the temporal-cache benchmark achieved a median of 30.6x speedup on cache hits. Beyond the speedup, our results expose a concrete failure mode of pure semantic caching for parameter-rich industrial queries, providing a critical analysis of how caching choices interact with evaluation correctness in MCP-backed agent benchmarks.